© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40135
    Prev
    Next
    INDEX
    Explanations

    careers and industry opportunities

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects references to practical, hands-on, real-world or experiential learning activities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctomy
    -1.15
     творо
    -1.10
     televisor
    -1.05
    zzá
    -1.00
    publik
    -0.97
    による
    -0.94
    isierte
    -0.93
    atorios
    -0.93
    контро
    -0.93
    OKER
    -0.93
    POSITIVE LOGITS
     career
    1.43
     careers
    1.25
     real
    1.15
     relevant
    1.09
     professional
    1.05
     industry
    1.05
     карьер
    1.03
     field
    1.00
     opportunities
    0.98
     exciting
    0.98
    Activations Density 0.045%

    No Known Activations